© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 12453
    Prev
    Next
    INDEX
    Explanations

    phrases related to institutions or structured systems

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to employment and work conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elcome
    -0.78
    Nusra
    -0.74
    ÄŁ
    -0.73
    conn
    -0.72
    worthiness
    -0.72
    veyard
    -0.69
    agen
    -0.68
    dam
    -0.67
    ippery
    -0.67
    hap
    -0.66
    POSITIVE LOGITS
     referen
    0.77
     entertainment
    0.76
     olds
    0.73
     IDE
    0.69
     guest
    0.67
     event
    0.66
     gorilla
    0.65
     approach
    0.65
     educational
    0.64
     enterprise
    0.64
    Activations Density 0.372%

    No Known Activations